lyndonkl Skills Library plugin

A Claude Code plugin marketplace with 260+ skills and 85 agents, from thinking and writing to company valuation

  • 196 ★ on the repository
  • Last commit
Plugin

Extended access

Why this level

  • Agents read and write project files and run external programs such as pandoc when a skill requires it
  • Some agents reach out to external data sources such as statements, market data and sports services
All reasons and checks

lyndonkl/claude

Install

Works in

In your terminal, with SkillFoxx CLI

npx skillfoxx add plugins/lyndonkl-skills-library

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Agents read and write project files and run external programs such as pandoc when a skill requires it
  • Some agents reach out to external data sources such as statements, market data and sports services

This is third-party code. Review the repository files before installing.

What it does

The lyndonkl/claude repository is a Claude Code plugin marketplace with a library of skills and orchestrating agents. The skills describe methods: thinking and decision frameworks, research, writing, design, data and machine learning, game theory, personal finance. An agent identifies the task and calls the right skills in sequence. Ready agent teams cover specific areas. A set of 15 agents values companies and deals, starting from `valuation-orchestrator`. Other groups run household finances from PDF statements, plan a conference schedule, help with manuscripts and grants, run a forecasting loop, build a narrative from research and write newsletter essays. There are non-business sets too, such as fantasy baseball. The plugin installs with two `/plugin` commands and opens every skill at once. Claude invokes them itself from the description in `SKILL.md`. Two skills lean on external tools: `markdown-to-pdf` on pandoc and LaTeX, `readability-check` on the Python package `textstat`.

Who it is for. Claude Code users who want ready-made methods for decisions, research and writing, and teams that assemble their own agent pipelines from existing ones.

Good fit when

  • A three-way choice turns into a criteria review and the agent builds a decision matrix
  • A manuscript, grant or recommendation letter goes through editing with a dedicated agent for scientific text
  • A company or project valuation is split into stages with a reviewer agent that attacks the finished calculation
  • Household finance PDF statements become a briefing and a dashboard with no manual sorting
  • A probability forecast is built in five phases with a calibration skill

Not a fit when

  • You need one narrow skill for a specific technology: the library covers methods and domains, not stacks
  • A money or legal decision rests on a licensed professional's opinion: agent calculations only prepare for it
  • A long skill list gets in the way: install only the plugin you need
  • You work outside Claude Code: the plugin relies on its `/plugin` mechanism

Example request

Help me choose between three architecture options: review them against criteria and build a decision matrix

Limitations

  • The license is not set up as a file: the README says the code is open and free to use with Claude Code, and individual skills carry their own attributions.
  • The README gives different skill counts in different places (261, 262 and 271), so check the exact number in the repository.
  • `markdown-to-pdf` needs pandoc and the `xelatex` LaTeX engine, and `readability-check` needs the Python package `textstat`. Without them those two skills exit with a ready install command while the rest work.
  • The last commit dates from August 2026.

How to disable. `/plugin uninstall` removes the installed plugin. For a manual install, delete the copied skill directories from `~/.claude/skills/`.

FAQ

How do I install the lyndonkl skills in Claude Code?

Run `/plugin marketplace add lyndonkl/claude`, then `/plugin install thinking-frameworks-skills`. After that every skill is available at once, and Claude invokes them from trigger phrases in the description.

How does an agent differ from a skill in this library?

A skill is a single method with its own `SKILL.md`, templates and evaluation rubric. An agent orchestrates several skills for a task: for example, `valuation-orchestrator` routes a company valuation to 14 specialists.

Can I install only part of the library?

Yes, the plugin installs in parts, and with a manual install you copy only the skill directories you need from `skills/` into `~/.claude/skills/`. Skills mention each other by name, but each is described separately.

Are extra programs required?

Not for most skills. `markdown-to-pdf` needs pandoc and `xelatex` (on macOS via `brew install pandoc basictex`), and `readability-check` needs `python3 -m pip install --user textstat`.

What happens if I run product-strategist without pandoc?

The agent still produces its main markdown report. Only the final PDF step fails, and the agent shows the install commands. You can render the report to PDF later.

Discussion

No questions or reviews yet.

Plugins

A large Claude Code plugin and skill marketplace with the ccpi CLI and a category-based catalog site

PluginExtended access2.9KRepository stars

11 skills for Claude Code: SKILL.md authoring, prompt tuning, refactoring, change review and planning in files.

SkillMinimal access286Repository stars

A personal Claude Code marketplace with 100+ skills: charts, codebase mapping, video, GitHub work and subagent dispatch.

PluginExtended access375Repository stars

A plugin with six working skills and a prompt library: routing a task to a prompt, pre-commit checks and skill audits.

PluginExtended access56Repository stars

A Claude Code plugin marketplace with ready sets of agents, slash commands, hooks and skills, plus a search site

PluginExtended access3.7KRepository stars

The author's personal Claude Code toolbox: meta-prompt and todo commands, skills to create skills, hooks and MCP servers, auditors and a Ralph loop

PluginBroad access2KRepository stars

Comparison with similar tools

Cards that share the main search query, and how they differ.

ToolOfficialRepository starsMain difference
lyndonkl Skills Library (this card)no196
Claude Skills (Alireza Rezvani)no29,704a library by development, marketing and product domains with C-level advisors, while lyndonkl focuses on thinking methods and agent chains
PM Skillsno27,935a marketplace for product managers, while lyndonkl is broader and covers company valuation, writing and finance

README in short

The page opens with a quick install and an "I want to..." table pointing to the right agent. It then covers a diagram of how agents and skills fit together, agent tables by domain, a skill index by category, installation as a plugin or by hand, example requests and contribution rules.

README badge

Report a problem